© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 15757
    Prev
    Next
    INDEX
    Explanations

    seeking clarification or permission

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     temprano
    -1.26
    เกี่ยวกับ
    -1.19
    怎么回事
    -1.19
     supuestamente
    -1.16
     Procu
    -1.12
    دور
    -1.12
    </h4>
    -1.11
    娣
    -1.11
     Haftung
    -1.10
     Traditionally
    -1.09
    POSITIVE LOGITS
    ?
    1.19
     this
    1.16
    leč
    1.13
    都能
    1.12
     gempa
    1.09
     that
    1.09
     must
    1.09
    チョイス
    1.09
    werkt
    1.05
     piemē
    1.05
    Activations Density 0.039%

    No Known Activations